Infinite data flow real-time privacy protection method and system based on dynamic budget allocation

Abstract

The invention discloses an infinite data flow real-time privacy protection method and system based on dynamic budget allocation, and the method comprises the steps: setting the length of a time window and a total privacy budget, carrying out the processing of the length of the time window and the total privacy budget, and obtaining the privacy budget of deviation calculation and distribution strategy selection; firstly, the current available budget is distributed, part of the budget is used for randomly disturbing original data locally, then the server gathers disturbed data, and the deviation between the statistical magnitude at the current moment and the statistical published value at the previous moment is estimated; and then selecting a publishing strategy by comparing the deviation with an error generated when the other part of budget is consumed to carry out statistical magnitude estimation. According to the method, higher-level local differential privacy protection can be provided at a user side, and meanwhile, the effectiveness of publishing data is improved by balancing the real-time change and the estimation error of the data stream. The method has rich application scenes and a good actual effect, the process is simple and easy to implement, and the expandability is high.

Description

technical field [0001] The invention belongs to the field of privacy protection, and in particular relates to a method and system for real-time privacy protection of unlimited data streams based on dynamic budget allocation. Background technique [0002] In recent years, with the rapid development of the Internet of Things and 5G technology, a large number of smart devices are flooding people's production and life, and interact with people and the surrounding environment at all times, which also brings massive data, which is widely collected , Convergence, storage, processing and analysis, which have created huge value for social production and life, and greatly improved people's living standards, such as traffic flow monitoring, personalized service recommendations, etc. However, precisely because these smart devices are closely related to people, the data they generate must also contain a large amount of personal privacy information, such as GPS tracks, health monitoring d...

AI Technical Summary

Problems solved by technology

However, the current localized differential privacy technology is only for static scenarios. For the real-time statistics and release of unlimited data streams in the perception system, the current related solutions are to design privacy-protected real-time data streams in centralized scenarios. The statistical release system lacks direct protection of the original local data flow, and the original data is collected centrally by data collectors, which still has great hidden dangers

Images